Search Results for author:
Found 5 papers, 1 papers with code
Mining Multi-Label Samples from Single Positive Labels
Therefore, in this study we explore the practical setting called the single positive setting, where each data instance is annotated by only one positive label with no explicit negative labels.
Residual Correction in Real-Time Traffic Forecasting
Extensive experiments on METR-LA and PEMS-BAY demonstrate that our ResCAL can correctly capture the correlation of errors and correct the failures of various traffic forecasting models in event situations.
Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
Existing deep interactive colorization models have focused on ways to utilize various types of interactions, such as point-wise color hints, scribbles, or natural-language texts, as methods to reflect a user's intent at runtime.
WaveBound: Dynamic Error Bounds for Stable Time Series Forecasting
Time series forecasting has become a critical task due to its high practicality in real-world applications such as traffic, energy consumption, economics and finance, and disease analysis.
Deep Imbalanced Time-series Forecasting via Local Discrepancy Density
Based on our findings, we propose a reweighting framework that down-weights the losses incurred by abrupt changes and up-weights those by normal states.
